Preparing, identifying, and classifying free text

Working with free text fields can be daunting. Parsing and understanding what these fields contain is a very difficult task and requires specialized tools to analyze them in detail.

We often use AI and ML models to do this, but in this recipe, we’ll explore a very easy yet powerful approach to parsing and classifying free text data.

Getting ready

For this recipe, you can download a test set from here: https://github.com/PacktPublishing/Alteryx-Designer-Cookbook/tree/main/ch5/Recipe1.

If you decide to try it with your own data, make sure you have at least a free text field and a dictionary of words to identify within that field.

We are going to read a series of free text transcriptions from customer service, and we want to classify them based on some keywords mentioned within those messages. We’ll assign a category based on a dictionary provided by the business unit, where a keyword corresponds to a category...